| { | |
| "best_metric": 0.6919782757759094, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.1902439024390246, | |
| "eval_steps": 25, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 0.2701288163661957, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7934, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "eval_loss": 1.0395761728286743, | |
| "eval_runtime": 1.603, | |
| "eval_samples_per_second": 31.191, | |
| "eval_steps_per_second": 8.11, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 0.4705568253993988, | |
| "learning_rate": 0.0001, | |
| "loss": 0.652, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.23414634146341465, | |
| "grad_norm": 0.5142024159431458, | |
| "learning_rate": 9.983788698441369e-05, | |
| "loss": 0.7973, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3121951219512195, | |
| "grad_norm": 0.2899770736694336, | |
| "learning_rate": 9.935271596564688e-05, | |
| "loss": 0.9691, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.3027752637863159, | |
| "learning_rate": 9.854798261200746e-05, | |
| "loss": 0.5577, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.4682926829268293, | |
| "grad_norm": 0.397220253944397, | |
| "learning_rate": 9.74294850457488e-05, | |
| "loss": 0.555, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.5463414634146342, | |
| "grad_norm": 0.579659640789032, | |
| "learning_rate": 9.600528206746612e-05, | |
| "loss": 0.6453, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.624390243902439, | |
| "grad_norm": 0.8211554884910583, | |
| "learning_rate": 9.428563509225347e-05, | |
| "loss": 0.576, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7024390243902439, | |
| "grad_norm": 0.3230455815792084, | |
| "learning_rate": 9.22829342159729e-05, | |
| "loss": 0.4713, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.2374473512172699, | |
| "learning_rate": 9.001160894432978e-05, | |
| "loss": 0.7677, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.8585365853658536, | |
| "grad_norm": 0.24319641292095184, | |
| "learning_rate": 8.74880242279536e-05, | |
| "loss": 0.4588, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.9365853658536586, | |
| "grad_norm": 0.3264821469783783, | |
| "learning_rate": 8.473036255255366e-05, | |
| "loss": 0.4458, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.0634146341463415, | |
| "grad_norm": 0.44675925374031067, | |
| "learning_rate": 8.175849293369291e-05, | |
| "loss": 1.2329, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.1414634146341462, | |
| "grad_norm": 0.22685877978801727, | |
| "learning_rate": 7.859382776007543e-05, | |
| "loss": 0.4817, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.2195121951219512, | |
| "grad_norm": 0.2206551730632782, | |
| "learning_rate": 7.525916851679529e-05, | |
| "loss": 0.4677, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.2975609756097561, | |
| "grad_norm": 0.19651265442371368, | |
| "learning_rate": 7.177854150011389e-05, | |
| "loss": 0.5962, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.3756097560975609, | |
| "grad_norm": 0.22256837785243988, | |
| "learning_rate": 6.817702470744477e-05, | |
| "loss": 0.3712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.4536585365853658, | |
| "grad_norm": 0.21558333933353424, | |
| "learning_rate": 6.448056714980767e-05, | |
| "loss": 0.4386, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.5317073170731708, | |
| "grad_norm": 0.2228691130876541, | |
| "learning_rate": 6.071580188860955e-05, | |
| "loss": 0.735, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.6097560975609757, | |
| "grad_norm": 0.25346508622169495, | |
| "learning_rate": 5.690985414382668e-05, | |
| "loss": 0.4369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.6878048780487804, | |
| "grad_norm": 0.19522270560264587, | |
| "learning_rate": 5.3090145856173346e-05, | |
| "loss": 0.4907, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.7658536585365854, | |
| "grad_norm": 0.1740201860666275, | |
| "learning_rate": 4.9284198111390456e-05, | |
| "loss": 0.6792, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.84390243902439, | |
| "grad_norm": 0.1370556354522705, | |
| "learning_rate": 4.551943285019234e-05, | |
| "loss": 0.3666, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.921951219512195, | |
| "grad_norm": 0.23627439141273499, | |
| "learning_rate": 4.182297529255525e-05, | |
| "loss": 0.4073, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "grad_norm": 0.41981157660484314, | |
| "learning_rate": 3.822145849988612e-05, | |
| "loss": 1.2191, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "eval_loss": 0.6919782757759094, | |
| "eval_runtime": 1.7192, | |
| "eval_samples_per_second": 29.083, | |
| "eval_steps_per_second": 7.562, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.126829268292683, | |
| "grad_norm": 0.15212808549404144, | |
| "learning_rate": 3.474083148320469e-05, | |
| "loss": 0.3673, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.204878048780488, | |
| "grad_norm": 0.22316193580627441, | |
| "learning_rate": 3.1406172239924584e-05, | |
| "loss": 0.4834, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.2829268292682925, | |
| "grad_norm": 0.1796901971101761, | |
| "learning_rate": 2.8241507066307104e-05, | |
| "loss": 0.636, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.3609756097560974, | |
| "grad_norm": 0.14367538690567017, | |
| "learning_rate": 2.5269637447446348e-05, | |
| "loss": 0.3709, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 0.16765695810317993, | |
| "learning_rate": 2.2511975772046403e-05, | |
| "loss": 0.4021, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.5170731707317073, | |
| "grad_norm": 0.1606360524892807, | |
| "learning_rate": 1.9988391055670233e-05, | |
| "loss": 0.6083, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.5951219512195123, | |
| "grad_norm": 0.12848107516765594, | |
| "learning_rate": 1.771706578402711e-05, | |
| "loss": 0.3334, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.6731707317073172, | |
| "grad_norm": 0.17367133498191833, | |
| "learning_rate": 1.5714364907746536e-05, | |
| "loss": 0.4383, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.7512195121951217, | |
| "grad_norm": 0.15716971457004547, | |
| "learning_rate": 1.3994717932533891e-05, | |
| "loss": 0.6039, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.8292682926829267, | |
| "grad_norm": 0.1574130654335022, | |
| "learning_rate": 1.257051495425121e-05, | |
| "loss": 0.3731, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.9073170731707316, | |
| "grad_norm": 0.18796025216579437, | |
| "learning_rate": 1.1452017387992552e-05, | |
| "loss": 0.4538, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.0341463414634147, | |
| "grad_norm": 0.3865165114402771, | |
| "learning_rate": 1.064728403435312e-05, | |
| "loss": 1.1283, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.1121951219512196, | |
| "grad_norm": 0.12527284026145935, | |
| "learning_rate": 1.0162113015586309e-05, | |
| "loss": 0.3601, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.1902439024390246, | |
| "grad_norm": 0.17297080159187317, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4422, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 39, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0058973260546048e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |